Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Improvised Linear Regression model to scout the best Manager for Manchester United

Download51 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343259,
        author={Manikandan  Rajagopal and Mansurali  A and Raja  P and Harish  V},
        title={Improvised Linear Regression model to scout the best Manager for Manchester United},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={football manager machine learning clustering random forest logistic regression multiple linear regression},
        doi={10.4108/eai.23-11-2023.2343259}
    }
    
  • Manikandan Rajagopal
    Mansurali A
    Raja P
    Harish V
    Year: 2024
    Improvised Linear Regression model to scout the best Manager for Manchester United
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343259
Manikandan Rajagopal1,*, Mansurali A2, Raja P2, Harish V3
  • 1: CHRIST(Deemed to be University), Bangalore
  • 2: Central University of Tamilnadu, India
  • 3: PSG Institute of Mangement, Coimbatore
*Contact email: manikandan.rajagopal@christuniversity.in

Abstract

The paper presents the efficacy of employing Artificial intelligence in sports analytics. The study envisages on the possibility of employing machine learning methodologies to aid in the decision-making procedure of identifying an appropriate manager for a football club through the utilization of machine learning models. This study is centered on the collection and analysis of data pertaining to managers within the top five leagues in Europe. The data pertaining to the pool of football managers that were available was subjected to pre-processing techniques and afterwards analysed in order to extract valuable insights on their historical performance. Subsequently, a variety of machine learning algorithms, including as clustering, random forest, logistic regression, and improved multiple linear regression, were employed to forecast the optimal manager for a club. The models underwent training using a dataset of historical performance data. Subsequently, their performance was assessed by comparing their predictions against actual outcomes, and metrics such as accuracy and F1 score. This study offers significant contributions to the utilization of machine learning models in addressing practical challenges within the sports business. The results of this study provide valuable insights for organizations encountering comparable difficulties and may serve as a point of reference for future investigations in this domain.